© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 3449
    Prev
    Next
    INDEX
    Explanations

    movement and arrival

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    an
    0.59
    ان
    0.54
    ل
    0.41
    ка
    0.40
    at
    0.40
    l
    0.40
    ك
    0.39
    కు
    0.38
    er
    0.37
    IC
    0.35
    POSITIVE LOGITS
     disgusted
    0.35
     frightened
    0.31
     invaded
    0.30
     calcium
    0.30
     commotion
    0.30
     irritable
    0.29
     threatening
    0.28
     uneasy
    0.28
     vegetation
    0.27
     darkened
    0.27
    Activations Density 0.184%

    No Known Activations